{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:57:40Z","timestamp":1771955860450,"version":"3.50.1"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585549","type":"print"},{"value":"9783030585556","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58555-6_18","type":"book-chapter","created":{"date-parts":[[2020,11,15]],"date-time":"2020-11-15T21:04:21Z","timestamp":1605474261000},"page":"294-311","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Knowledge Transfer via Dense Cross-Layer Mutual-Distillation"],"prefix":"10.1007","author":[{"given":"Anbang","family":"Yao","sequence":"first","affiliation":[]},{"given":"Dawei","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,16]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Aguilar, G., Ling, Y., Zhang, Y., Yao, B., Fan, X., Guo, C.: Knowledge distillation from internal representations. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i05.6229"},{"key":"18_CR2","unstructured":"Ba, L.J., Caruana, R.: Do deep nets really need to be deep? In: NIPS (2014)"},{"key":"18_CR3","unstructured":"Batra, T., Parikh, D.: Cooperative learning with visual attributes. arXiv preprint arXiv:1705.05512 (2017)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT (1998)","DOI":"10.1145\/279943.279962"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Bucil\u01ce, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: KDD (2006)","DOI":"10.1145\/1150402.1150464"},{"key":"18_CR6","unstructured":"Chen, T., Goodfellow, I., Shlens, J.: Net2Net: accelerating learning via knowledge transfer. In: ICLR (2016)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"18_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-030-01237-3_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"NC Garcia","year":"2018","unstructured":"Garcia, N.C., Morerio, P., Murino, V.: Modality distillation with multiple stream networks for action recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 106\u2013121. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_7"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"18_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1007\/978-3-030-01252-6_30","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Guo","year":"2018","unstructured":"Guo, X., Li, H., Yi, S., Ren, J., Wang, X.: Learning monocular depth by distilling cross-domain stereo networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 506\u2013523. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_30"},{"key":"18_CR11","unstructured":"Hafner, F., Bhuiyan, A., Kooij, J.F.P., Granger, E.: A cross-modal distillation network for person re-identification in RGB-depth. arXiv preprint arXiv:1810.11641 (2018)"},{"key":"18_CR12","unstructured":"He, D., et al.: Dual learning for machine translation. In: NIPS (2017)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR14","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"18_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1007\/978-3-030-01219-9_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Hou","year":"2018","unstructured":"Hou, S., Pan, X., Loy, C.C., Wang, Z., Lin, D.: Lifelong learning via progressive distillation and retrospection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 452\u2013467. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_27"},{"key":"18_CR16","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"18_CR18","unstructured":"Huang, G., Chen, D., Li, T., Wu, F., van der Maaten, L., Weinberger, K.Q.: Multi-scale dense networks for resource efficient image classification. In: ICLR (2018)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"18_CR20","unstructured":"Jia, S., Bruce, N.D.B.: Richer and deeper supervision network for salient object detection. arXiv preprint arXiv:1901.02425 (2018)"},{"key":"18_CR21","unstructured":"Kim, J., Park, S., Kwak, N.: Paraphrasing complex network: network compression via factor transfer. In: NeurIPS (2018)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Kim, Y., Rush, A.M.: Sequence-level knowledge distillation. In: EMNLP (2016)","DOI":"10.18653\/v1\/D16-1139"},{"key":"18_CR23","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. In: Tech Report (2009)"},{"key":"18_CR24","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Lakkakula, N., Babu, R.V.: UM-Adapt: unsupervised multi-task adaptation using adversarial cross-task distillation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00152"},{"key":"18_CR26","unstructured":"Lan, X., Zhu, X., Gong, S.: Knowledge distillation by on-the-fly native ensemble. In: NeurIPS (2018)"},{"key":"18_CR27","unstructured":"Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: AISTATS (2015)"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Lee, S.H., Kim, H.D., Song, B.C.: Self-supervised knowledge distillation using singular value decomposition. In: NeurIPS (2018)","DOI":"10.1007\/978-3-030-01231-1_21"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, N., Liu, J., Hou, X.: Demystifying neural style transfer. In: IJCAI (2016)","DOI":"10.24963\/ijcai.2017\/310"},{"key":"18_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1007\/978-3-319-46493-0_37","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Li","year":"2016","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 614\u2013629. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_37"},{"key":"18_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"18_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"18_CR34","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch. In: NIPS Workshops (2017)"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Phuong, M., Lampert, C.H.: Distillation-based training for multi-exit architectures. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00144"},{"key":"18_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-030-01267-0_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Qiao","year":"2018","unstructured":"Qiao, S., Shen, W., Zhang, Z., Wang, B., Yuille, A.: Deep co-training for semi-supervised image recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 142\u2013159. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_9"},{"key":"18_CR37","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. In: ICLR (2015)"},{"issue":"3","key":"18_CR38","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"18_CR41","unstructured":"Song, G., Chai, W.: Collaborative learning for deep neural networks. In: NeurIPS (2018)"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Sun, D., Yao, A., Zhou, A., Zhao, H.: Deeply-supervised knowledge synergy. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00716"},{"issue":"12","key":"18_CR43","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","volume":"105","author":"V Sze","year":"2017","unstructured":"Sze, V., Chen, Y.H., Yang, T.J., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295\u20132329 (2017)","journal-title":"Proc. IEEE"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"18_CR45","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. In: ICLR (2020)"},{"key":"18_CR46","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. ICLR (2020)"},{"key":"18_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/978-3-319-46484-8_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Wang","year":"2016","unstructured":"Wang, Z., Deng, Z., Wang, S.: Accelerating convolutional neural networks with dominant convolutional kernel and knowledge pre-regression. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 533\u2013548. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_32"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Wang, X., Nicu, S.: PAD-Net: multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00077"},{"key":"18_CR51","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.754"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. In: BMVC (2016)","DOI":"10.5244\/C.30.87"},{"key":"18_CR53","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: ICLR (2017)"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Zhai, M., Chen, L., Tung, F., He, J., Nawhal, M., Mori, G.: Lifelong GAN: continual learning for conditional image generation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00285"},{"key":"18_CR55","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. In: ICLR (2017)"},{"key":"18_CR56","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR (2018)"},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"18_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-030-01249-6_17","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Zhang, X., Peng, C., Xue, X., Sun, J.: ExFuse: enhancing feature fusion for semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 273\u2013288. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_17"},{"key":"18_CR59","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58555-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:10:44Z","timestamp":1731629444000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58555-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585549","9783030585556"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58555-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"16 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}